Trustworthy and Explainable Artificial Intelligence for Reliable Bank Term Deposit Subscription Prediction
DOI:
https://doi.org/10.66279/016z8w59Keywords:
Trustworthy, Explainable Artificial Intelligence, Bank Term Deposit, Subscription Prediction, UCI Bank MarketingAbstract
Predicting subscription to a bank term deposit is a highly imbalanced binary classification problem in which apparently strong performance can result from information that is unavailable at the time of targeting. This study develops and audits a leakage aware prediction pipeline using the UCI Bank Marketing dataset. The analysis compares logistic regression with XGBoost, LightGBM, and CatBoost, evaluates class imbalance treatments, performs hyperparameter optimization, examines probability calibration, and adds model agnostic and model specific explanations. The post call duration variable is excluded from the deployable feature set and retained only for a controlled leakage experiment. Five fold cross validation on the training partition gives realistic ROC AUC values from 0.7519 to 0.7959, whereas inclusion of duration increases the corresponding values to 0.8966 to 0.9375. On the untouched random test partition, the calibrated LightGBM model obtains ROC AUC 0.8101, average precision 0.4698, and Brier score 0.0795. An inferred chronological stress test produces ROC AUC 0.7089, demonstrating that random partition estimates can overstate temporal portability. Under illustrative unit economics, a threshold selected from training set out of fold predictions increases test set expected profit from 16,595 to 41,825 units. These findings support a practical principle: leakage control, temporal validation, calibration, and decision analysis are more consequential than small differences among strong tree boosting algorithms.
Downloads
References
[1] S. Moro, P. Cortez, and P. Rita, “A data-driven approach to predict the success of bank telemarketing,” Decision Support Systems, vol. 62, pp. 22–31, 2014. DOI: https://doi.org/10.1016/j.dss.2014.03.001
[2] S. Moro, P. Rita, and P. Cortez, “Bank marketing,” 2014. Repository record donated in 2012; dataset citation issued in 2014.
[3] G. Marinakos and S. Daskalaki, “Imbalanced customer classification for bank direct marketing,” Journal of Marketing Analytics, vol. 5, no. 1, pp. 14–30, 2017. DOI: https://doi.org/10.1057/s41270-017-0013-7
[4] S. C. K. Tékouabou, Ş. C. Gherghina, H. Toulni, P. Neves Mata, M. N. Mata, and J. M. Martins, “A machine learning framework towards bank telemarketing prediction,” Journal of Risk and Financial Management, vol. 15, no. 6, p. 269, 2022. DOI: https://doi.org/10.3390/jrfm15060269
[5] S. F. Crone, S. Lessmann, and R. Stahlbock, “The impact of preprocessing on data mining: An evaluation of classifier sensitivity in direct marketing,” European Journal of Operational Research, vol. 173, no. 3, pp. 781–800, 2006. DOI: https://doi.org/10.1016/j.ejor.2005.07.023
[6] E. Duman, Y. Ekinci, and A. Tanrıverdi, “Comparing alternative classifiers for database marketing: The case of imbalanced datasets,” Expert Systems with Applications, vol. 39, no. 1, pp. 48–53, 2012. DOI: https://doi.org/10.1016/j.eswa.2011.06.048
[7] T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp. 785–794, 2016. DOI: https://doi.org/10.1145/2939672.2939785
[8] G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T.-Y. Liu, “Lightgbm: A highly efficient gradient boosting decision tree,” Advances in neural information processing systems, vol. 30, 2017.
[9] L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, and A. Gulin, “Catboost: unbiased boosting with categorical features,” Advances in neural information processing systems, vol. 31, 2018.
[10] Y. Gorishniy, I. Rubachev, V. Khrulkov, and A. Babenko, “Revisiting deep learning models for tabular data,” Advances in neural information processing systems, vol. 34, pp. 18932–18943, 2021.
[11] T. Saito and M. Rehmsmeier, “The precision-recall plot is more informative than the roc plot when evaluating binary classifiers on imbalanced datasets,” PloS one, vol. 10, no. 3, p. e0118432, 2015. DOI: https://doi.org/10.1371/journal.pone.0118432
[12] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “Smote: synthetic minority over-sampling technique,” Journal of artificial intelligence research, vol. 16, pp. 321–357, 2002. DOI: https://doi.org/10.1613/jair.953
[13] A. Atwa, A. Y. Ismaeel, and A. A. Elngar, “Machine learning for chronic disease classification and comorbidity detection: Methodological gaps and future directions,” Journal of Smart Algorithms and Applications (JSAA), vol. 3, no. 2, pp. 87–104, 2026. DOI: https://doi.org/10.66279/5a6sr902
[14] A. Niculescu-Mizil and R. Caruana, “Predicting good probabilities with supervised learning,” in Proceedings of the 22nd international conference on Machine learning, pp. 625–632, 2005. DOI: https://doi.org/10.1145/1102351.1102430
[15] S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” Advances in neural information processing systems, vol. 30, 2017.
[16] J. Demšar, “Statistical comparisons of classifiers over multiple data sets,” Journal of Machine learning research, vol. 7, no. Jan, pp. 1–30, 2006.
[17] S. Moro, P. Rita, and P. Cortez, “Bank marketing,” 2014. Dataset documentation accessed August 26, 2026.
[18] D. R. Cox, “The regression analysis of binary sequences,” Journal of the Royal Statistical Society Series B: Statistical Methodology, vol. 20, no. 2, pp. 215–232, 1958. DOI: https://doi.org/10.1111/j.2517-6161.1958.tb00292.x
[19] D. H. Wolpert, “Stacked generalization,” Neural networks, vol. 5, no. 2, pp. 241–259, 1992. DOI: https://doi.org/10.1016/S0893-6080(05)80023-1
[20] C. Elkan, “The foundations of cost-sensitive learning,” in Proceedings of the International Joint Conference on Artificial Intelligence, vol. 17, pp. 973–978, 2001.
[21] A. H. Murphy, “A new vector partition of the probability score,” Journal of Applied Meteorology and Climatology, vol. 12, no. 4, pp. 595–600, 1973. DOI: https://doi.org/10.1175/1520-0450(1973)012<0595:ANVPOT>2.0.CO;2
[22] M. Hardt, E. Price, and N. Srebro, “Equality of opportunity in supervised learning,” Advances in neural information processing systems, vol. 29, 2016.
[23] M. Feldman, S. A. Friedler, J. Moeller, C. Scheidegger, and S. Venkatasubramanian, “Certifying and removing disparate impact,” in Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 259–268, 2015. DOI: https://doi.org/10.1145/2783258.2783311
Downloads
Published
Data Availability Statement
The Bank Marketing dataset used in this study is publicly available from the UCI Machine Learning Repository at https://archive.ics.uci.edu/dataset/222/bank+marketing and is identified by DOI 10.24432/C5K306 [2].
Issue
Section
Categories
License
Copyright (c) 2026 Computational Discovery and Intelligent Systems (CDIS)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Computational Discovery and Intelligent Systems (CDIS) content is published under a Creative Commons Attribution 4.0 International (CC BY 4.0) License. This means that content is freely available to all readers upon publication, and content is published as soon as production is complete.
Computational Discovery and Intelligent Systems (CDIS) seeks to publish the most influential papers that will significantly advance scientific understanding. Selected articles must present new and widely significant data, syntheses, or concepts. They should merit recognition by the wider scientific community and the general public through publication in a reputable scientific journal.
As well as the content, this is published under a Creative Commons Attribution 4.0 International (CC BY 4.0) License. This means that content is freely available to all readers upon publication, and content is published as soon as production is complete.
SIRG Publisher
